LIMIT DISTRIBUTIONS AND SENSITIVITY ANALYSIS FOR EMPIRICAL ENTROPIC OPTIMAL TRANSPORT ON COUNTABLE SPACES

• 成果类型: Article
• 署名作者: Hundrieser, Shayan; Klatt, Marcel; Munk, Axel
• 署名单位: University of Gottingen
• 刊物名称: ANNALS OF APPLIED PROBABILITY
• ISSN/ISSBN: 1050-5164
• DOI: 10.1214/23-AAP1995
• 发表日期: 2024
• 页码: 1403-1468
• 关键词: regularized optimal transport; algorithms; inference; matrices

摘要

For probability measures on countable spaces we derive distributional limits for empirical entropic optimal transport quantities. More precisely, we show that the empirical optimal transport plan weakly converges to a centered Gaussian process and that the empirical entropic optimal transport value is asymptotically normal. The results are valid for a large class of cost functions and generalize distributional limits for empirical entropic optimal transport quantities on finite spaces. Our proofs are based on a sensitivity analysis with respect to norms induced by suitable function classes, which arise from novel quantitative bounds for primal and dual optimizers, that are related to the exponential penalty term in the dual formulation. The distributional limits then follow from the functional delta method together with weak convergence of the empirical process in that respective norm, for which we provide sharp conditions on the underlying measures. As a byproduct of our proof technique, consistency of the bootstrap for statistical applications is shown.